期刊名称：International Journal of Engineering and Computer Science
印刷版ISSN：2319-7242
出版年度：2014
卷号：3
期号：10
页码：8765-8771
出版社：IJECS
摘要：Temporal segmentation of facial gestures in spontaneous facial behavior recorded in real-world settings is an important, unsolved,and relatively unexplored problem in facial image analysis. Several issues contribute to the challenge of this task. These include non-frontalpose, moderate to large out-of-plane head motion, large variability in the temporal scale of facial gestures, and the exponential nature of possiblefacial action combinations. To address these challenges, we propose a two-step approach to temporally segment facial behavior. The first stepuses spectral graph techniques to cluster shape and appearance features invariant to some geometric transformations. The second step groups theclusters into temporally coherent facial gestures. We evaluated this method in facial behavior recorded during face-to-face interactions. Thevideo data were originally collected to answer substantive questions in psychology without concern for algorithm development. The methodachieved moderate convergent validity with manual FACS (Facial Action Coding System) annotation. Further, when used to preprocess videofor manual FACS annotation, the method significantly improves productivity, thus addressing the need for ground-truth data for facial imageanalysis. Moreover, we were also able to detect unusual facial behavior. This paper consists of efficient facial detection in static images usingHistogram of Oriented Gradients (HOG) for local feature extraction and linear piecewise support vector machine (PL-SVM) classifiers.Histogram of oriented gradient (HOG) gives an accurate description of the contour of image. HOG features are calculated by taking orientationof histogram of edge intensity in a local region. PL-SVM is nonlinear classifier that can discriminate multi-view and multi-posture from theimages in high dimensional feature space. Each PL-SVM model forms the subspace, corresponding to the cluster of special view. This paperconsists of comparison of PL-SVM and several recent SVM methods in terms of cross validation accuracy
关键词：Facial detection; histogram of oriented gradients; classification; support vector machine
